In this paper, the integration of artificial neural networks and genetic algorithms is explored for solving uncured composite stock cutting problem, which is an NP-complete problem. The input patterns can be either rectangular or irregular, and the proposed approach can accommodate any orientation and size restrictions. A genetic algorithm is used to generate sequences of the input patterns to be allocated. The scrap percentage of each allocation is used as an evaluation criterion. The allocation algorithm uses the sliding method integrated with an artificial neural network, based on the adaptive resonance theory (ART1) paradigm, to allocate the patterns according to the sequence generated by the genetic algorithm. The results obtained by this approach give packing densities on the order of 80-95%.
P. Poshyanonda and C. H. Dagli, "Genetic Neuro-nester," Journal of Intelligent Manufacturing, Springer Verlag, Jan 2004.
The definitive version is available at https://doi.org/10.1023/B:JIMS.0000018033.05556.65
Engineering Management and Systems Engineering
Keywords and Phrases
Nesting; Genetic Algorithms; Neural Networks; Optimization
Article - Journal
© 2004 Springer Verlag, All rights reserved.